6533b838fe1ef96bd12a3a52
RESEARCH PRODUCT
Speech-input multi-target machine translation
M. Teresa GonzálezFrancisco CasacubertaAlicia PérezM. Inés Torressubject
Multi targetMachine translationComputer Science::SoundComputer scienceSpeech translationSpeech recognitionSpeech inputComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Extension (predicate logic)computer.software_genrecomputerDecoding methodsdescription
In order to simultaneously translate speech into multiple languages an extension of stochastic finite-state transducers is proposed. In this approach the speech translation model consists of a single network where acoustic models (in the input) and the multilingual model (in the output) are embedded. The multi-target model has been evaluated in a practical situation, and the results have been compared with those obtained using several mono-target models. Experimental results show that the multi-target one requires less amount of memory. In addition, a single decoding is enough to get the speech translated into multiple languages.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2007-01-01 | Proceedings of the Second Workshop on Statistical Machine Translation - StatMT '07 |